Lung cancer is the most common fatal malignancy in both men and women. Early detection and treatment of lung cancer can drastically improve the survival rate of patients. Therefore, there is a great need for a new technology to diagnose the lung cancer in its early stages. In this area, Computerized tomography (CT) is considered as the best imaging modality for identification of anatomy's defect. There are a lot of medical image processing software tools for research and diagnostic aims, including data gathering in image and algorithms for analysis of the new images and eventually for testing the systems result. To achieve this and to diagnose the area of the cancer mass, two methods are presented in this paper, and the area of abnormality space is calculated. One of the techniques for diagnosing unusual mass is Graph classification method. In this paper, component of images are classified and displayed as a set of points and edges with graph method. In the other method, changes in colors in the surrounding area are examined. In the end, the results of the two techniques are compared and the accuracy of the algorithm is tested. Experiments show that the proposed method has improved significantly in mass detection and the sensitivity of the proposed system is up to 90%, which shows that the proposed method can help the radiologists to increase their diagnostic confidence.