Breast cancer is the most common cancer in women around the world. Various countries including the UAE offer asymptomatic screening for the disease. The interpretation of mammograms is a very challenges task and is subject to human error. Computer-aided detection and diagnosis have been proposed as a second reader for helping radiologists perform this difficult task. Texture features have been widely used as classification of masses in digital mammogram. In this paper we proposed a method for automatic detection of masses in digital mammogram. The proposed method uses the coding technique achieved good accuracy with Linear Discriminant Analysis (LDA) classification. The classification accuracy by using the coded images is improved much compared to one that obtained from the original image.