The diagnosis of tuberculosis and lung cancer is difficult, as symptoms of both diseases are similar. Due to high TB prevalence and radiological similarities, a large number of lung cancer patients initially get wrongly treated for tuberculosis based on radiological picture alone. However, treating TB leads to inflammatory fibrosis in some of the patients. In all these cases, the diagnosis is confirmed only with a biopsy which is an invasive technique that is usually performed via Bronchoscopy or CT – guided biopsy. There comes the need of an efficient Computer Aided Diagnosis(CAD) of the fibrosis and adenocarcinoma diseases. The increased chance of characterizing tissues with the help of CAD and the achievable workload reduction for the radiologist demand the usage of these systems in CT screenings as well as daily hospital practice. Generally, the CAD is designed based on the Region of Interest(ROI) given by the radiologist which makes the system semi-automatic. Our work presents a fully automated method of characterization of carcinoma from other lung abnormalities namely fibrosis and suspicious of tuberculosis. A comparison study is also done by evaluating the performance of Adaptive Neuro-Fuzzy Inference System(ANFIS) as a Classifier with three set of features. These feature set include entropy and parameters extracted by Gray Level Co-Occurrence Matrix(GLCM) and Gray Level Run Length Matrix(GLRLM).