As Big Data is making a paradigm shift into the healthcare industry and clinical treatments of patients for the cancer research and diagnosis, making a robust analytical platform to combine the financial and clinical outcomes is becoming the most prominent concern these days. Big Data Performance Analytics requires tools that could deal with the ever rising and growing data volumes and the velocity through which it could evaluate results swiftly and bring value to the diagnosis and treatment. Despite having the AI/ML models to predict the results of cancer patients some results don’t tend to work on variety of different factors that slowly leads to degrade the research results. So, the resilient Big Data Systems are the need of the hour which are highly reliable and can make the timely strategic and operational decisions using the immediately actionable information. The main goal of this work is to bridge the void’s that are still prevailing among the quantitative representation of quality concepts that researchers and engineers could work together. For this, Statistical methods, Anomaly Detection and classifying predictive trends through Map-Reduce by leveraging the Cloud Computing would be an efficient approach to evaluate the performance measures. Thus, in the ever-changing landscape of dynamic research for cancer patient treatments, performance analytics to interpret the results and specification for the treatments are the primary thing to be resolved. Overall, extensive experimentation is required to integrate the novel outcomes with the existing techniques paying ways to new set of approaches.