Non-small cell lung cancer (NSCLC) accounts for 85% of all the lung cancers. Noninvasive identification of the histology of NSCLC aids in determining the appropriate treatment approaches. In this study, we have analyzed the usage of radiomics with application of fractals to arrive at the histology classification of NSCLC using lung CT images. This study suggests that fractals can play a vital role in radiomics by providing information about the gross tumor volume (GTV) structure, and helping in the characterization of the tumor. It was observed that fractal dimension–based features were among the top 15 features that aided in histology classification based on 317 subjects, and that they improved the existing classification accuracy of the NSCLC histology by 8% by adding fractal dimension as a feature.