Hi Marc
concerning the optimization loop nodes you might check this workflow: https://hub.knime.com/knime/spaces/Examples/latest/04_Analytics/11_Optimization/07_Cross_Validation_with_SVM_and_Parameter_Optimization . It uses SVM, but gives a nice overview about how to combine crossvalidation and parameter optimization.
The output of Random Forest and Tree Ensemble are identical, as the RF nodes are just an easier version of the TE nodes. Considering that you can use the solution in the forum link that you posted (How to get the variable importance from the Random Forest model? I also updated the link to the slides there).
Hope that helps!
Best
Alice