Over the last few years the field of radiomics has been gaining ground in the field of nuclear medicine and in multimodality imaging. Within this context, numerous studies have exploited the potential interest of radiomics in clinical practice, within the diagnostic field as well as in prognostic and predictive modeling of patient response. Although these studies have showed some interesting results, there are also persistent conflicting conclusions. Most of these studies suffer from consistently low number of patients, lack of external dataset based validation of most frequently single center determined models and non-standardised calculation of radiomics features. In the future, clear identification of the most pertinent applications of clinical utilization in combination with multi-center studies will allow more concrete clinical applications of radiomics to be identified. In addition, the recent interest of artificial intelligence which can completely change the current paradigm of radiomics use in clinical practice needs to be integrated within this framework. This paper highlights the main areas of radiomics applications considered up to date and provides an insight on the main issues and potential solutions in order to allow a potential future integration in clinical practice.