Diabetic retinopathy (DR) is one of the leading causes of blindness around the world. It is known for its effect on the working age population. It appears as a complication of diabetes which affects the blood vessels in the retina. One way to reduce the severity of the disease is its early diagnosis. We propose a comprehensive computer aided diagnosis (CAD) system for the early detection of DR. Our system uses both optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) to detect the disease. We were able to segment the blood vessels from a set of OCTA scans as well as segmenting 12 layers of the retina from OCT scans. To be able to diagnose this disease, we were able to extract five features from both OCT and OCTA. These features are fed to a support vector machine to classify these images into diseased and not-diseased. Using four-fold cross validation and an SVM classifier, our CAD system achieved an accuracy of 97%.