Large bowel obstruction occurs when there is a blockage or twisting in the large bowel that prevents wastes and gas from passing through. The blockage cuts off blood supply to the bowel and a part of the bowel dies. And highest morbidity and mortality rates if left untreated. The examination of clinical symptoms of large bowel obstruction involves careful inspection of the cecum and colon. Radiologists use X-radiation to inspect the clinical signs. Some research has been done to automate detecting related abdominal and intestinal diseases. However, all the above studies concentrate only on detecting Crohn’s, ulcerative colitis, Acute Appendicitis, colorectal cancer, celiac diseases, liver diseases, and chronic kidney. Detection and classification of LBO have not been given due attention so far. To contribute to this limitation, we have designed a model for the detection and classification of large bowel obstruction. We collected the dataset from Addis abeba tikur anbesa specialized hospital, Gonder university specialized hospital, and debark specialized hospital. Our model includes preprocessing, detection, segmentation, feature extraction, and classification components. We have to propose a gray scale level co-occurrence matrix (GLCM), and a convolutional neural network for feature extraction. We used the support vector machine (SVM) and softmax for classification. Our model achieved a diagnostic accuracy of feature extraction methods with CNN and median filter with softmax classifier achieved 89%. CNN and Gaussian filter with soft max classifier achieved 91%. CNN and anisotropic filter with soft max classifier achieved 92%. GLCM with threshold segmentation and Gaussian filter with SVM classifier achieved 87%. CNN with watershed segmentation and Gaussian filter with SVM classifier achieved 97%. And CNN-GLCM with watershed segmentation and anisotropic diffusion filter with SVM classifier achieved 98% to classify LBO. Therefore, finally, this thesis aims to classification of large bowel obstruction using machine learning approaches. Hence, our model is designed to assist human experts (Radiologists) in diagnosing large bowel obstruction.